{"id":15028144,"url":"https://github.com/wzhe06/sparrowrecsys","last_synced_at":"2025-04-11T06:23:08.222Z","repository":{"id":41321570,"uuid":"261366056","full_name":"wzhe06/SparrowRecSys","owner":"wzhe06","description":"A Deep Learning Recommender System","archived":false,"fork":false,"pushed_at":"2024-06-02T04:38:14.000Z","size":66590,"stargazers_count":2501,"open_issues_count":24,"forks_count":844,"subscribers_count":56,"default_branch":"master","last_synced_at":"2025-04-03T07:08:27.714Z","etag":null,"topics":["deep-learning","machine-learning","recommender-system"],"latest_commit_sha":null,"homepage":"http://wzhe.me/SparrowRecSys/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/wzhe06.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2020-05-05T05:03:23.000Z","updated_at":"2025-04-03T05:31:02.000Z","dependencies_parsed_at":"2024-11-11T10:42:33.033Z","dependency_job_id":null,"html_url":"https://github.com/wzhe06/SparrowRecSys","commit_stats":{"total_commits":85,"total_committers":13,"mean_commits":6.538461538461538,"dds":0.4117647058823529,"last_synced_commit":"579577c9a25f75fc6bbdfeb2f258f7c8a35833dd"},"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wzhe06%2FSparrowRecSys","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wzhe06%2FSparrowRecSys/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wzhe06%2FSparrowRecSys/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wzhe06%2FSparrowRecSys/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/wzhe06","download_url":"https://codeload.github.com/wzhe06/SparrowRecSys/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248352542,"owners_count":21089463,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["deep-learning","machine-learning","recommender-system"],"created_at":"2024-09-24T20:07:41.999Z","updated_at":"2025-04-11T06:23:08.195Z","avatar_url":"https://github.com/wzhe06.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# SparrowRecSys\nSparrowRecSys是一个电影推荐系统，名字SparrowRecSys（麻雀推荐系统），取自“麻雀虽小，五脏俱全”之意。项目是一个基于maven的混合语言项目，同时包含了TensorFlow，Spark，Jetty Server等推荐系统的不同模块。希望你能够利用SparrowRecSys进行推荐系统的学习，并有机会一起完善它。\n\n## 基于SparrowRecSys的实践课程\n受极客时间邀请开设 [深度学习推荐系统实战](http://gk.link/a/10lyE) 课程，详细讲解了SparrowRecSys的所有技术细节，覆盖了深度学习模型结构，模型训练，特征工程，模型评估，模型线上服务及推荐服务器内部逻辑等模块。\n\n## 环境要求\n* Java 8\n* Scala 2.11\n* Python 3.6+\n* TensorFlow 2.0+\n\n## 快速开始\n将项目用IntelliJ打开后，找到`RecSysServer`，右键点选`Run`，然后在浏览器中输入`http://localhost:6010/`即可看到推荐系统的前端效果。\n\n## 项目数据\n项目数据来源于开源电影数据集[MovieLens](https://grouplens.org/datasets/movielens/)，项目自带数据集对MovieLens数据集进行了精简，仅保留1000部电影和相关评论、用户数据。全量数据集请到MovieLens官方网站进行下载，推荐使用MovieLens 20M Dataset。\n\n## SparrowRecSys技术架构\nSparrowRecSys技术架构遵循经典的工业级深度学习推荐系统架构，包括了离线数据处理、模型训练、近线的流处理、线上模型服务、前端推荐结果显示等多个模块。以下是SparrowRecSys的架构图：\n![alt text](https://github.com/wzhe06/SparrowRecSys/raw/master/docs/sparrowrecsysarch.png)\n\n## SparrowRecSys实现的深度学习模型\n* Word2vec (Item2vec)\n* DeepWalk (Random Walk based Graph Embedding)\n* Embedding MLP\n* Wide\u0026Deep\n* Nerual CF\n* Two Towers\n* DeepFM\n* DIN(Deep Interest Network)\n\n## 相关论文\n* [[FFM] Field-aware Factorization Machines for CTR Prediction (Criteo 2016)](https://github.com/wzhe06/Ad-papers/blob/master/Classic%20CTR%20Prediction/%5BFFM%5D%20Field-aware%20Factorization%20Machines%20for%20CTR%20Prediction%20%28Criteo%202016%29.pdf) \u003cbr /\u003e\n* [[GBDT+LR] Practical Lessons from Predicting Clicks on Ads at Facebook (Facebook 2014)](https://github.com/wzhe06/Ad-papers/blob/master/Classic%20CTR%20Prediction/%5BGBDT%2BLR%5D%20Practical%20Lessons%20from%20Predicting%20Clicks%20on%20Ads%20at%20Facebook%20%28Facebook%202014%29.pdf) \u003cbr /\u003e\n* [[PS-PLM] Learning Piece-wise Linear Models from Large Scale Data for Ad Click Prediction (Alibaba 2017)](https://github.com/wzhe06/Ad-papers/blob/master/Classic%20CTR%20Prediction/%5BPS-PLM%5D%20Learning%20Piece-wise%20Linear%20Models%20from%20Large%20Scale%20Data%20for%20Ad%20Click%20Prediction%20%28Alibaba%202017%29.pdf) \u003cbr /\u003e\n* [[FM] Fast Context-aware Recommendations with Factorization Machines (UKON 2011)](https://github.com/wzhe06/Ad-papers/blob/master/Classic%20CTR%20Prediction/%5BFM%5D%20Fast%20Context-aware%20Recommendations%20with%20Factorization%20Machines%20%28UKON%202011%29.pdf) \u003cbr /\u003e\n* [[DCN] Deep \u0026 Cross Network for Ad Click Predictions (Stanford 2017)](https://github.com/wzhe06/Ad-papers/blob/master/Deep%20Learning%20CTR%20Prediction/%5BDCN%5D%20Deep%20%26%20Cross%20Network%20for%20Ad%20Click%20Predictions%20%28Stanford%202017%29.pdf) \u003cbr /\u003e\n* [[Deep Crossing] Deep Crossing - Web-Scale Modeling without Manually Crafted Combinatorial Features (Microsoft 2016)](https://github.com/wzhe06/Ad-papers/blob/master/Deep%20Learning%20CTR%20Prediction/%5BDeep%20Crossing%5D%20Deep%20Crossing%20-%20Web-Scale%20Modeling%20without%20Manually%20Crafted%20Combinatorial%20Features%20%28Microsoft%202016%29.pdf) \u003cbr /\u003e\n* [[PNN] Product-based Neural Networks for User Response Prediction (SJTU 2016)](https://github.com/wzhe06/Ad-papers/blob/master/Deep%20Learning%20CTR%20Prediction/%5BPNN%5D%20Product-based%20Neural%20Networks%20for%20User%20Response%20Prediction%20%28SJTU%202016%29.pdf) \u003cbr /\u003e\n* [[DIN] Deep Interest Network for Click-Through Rate Prediction (Alibaba 2018)](https://github.com/wzhe06/Ad-papers/blob/master/Deep%20Learning%20CTR%20Prediction/%5BDIN%5D%20Deep%20Interest%20Network%20for%20Click-Through%20Rate%20Prediction%20%28Alibaba%202018%29.pdf) \u003cbr /\u003e\n* [[ESMM] Entire Space Multi-Task Model - An Effective Approach for Estimating Post-Click Conversion Rate (Alibaba 2018)](https://github.com/wzhe06/Ad-papers/blob/master/Deep%20Learning%20CTR%20Prediction/%5BESMM%5D%20Entire%20Space%20Multi-Task%20Model%20-%20An%20Effective%20Approach%20for%20Estimating%20Post-Click%20Conversion%20Rate%20%28Alibaba%202018%29.pdf) \u003cbr /\u003e\n* [[Wide \u0026 Deep] Wide \u0026 Deep Learning for Recommender Systems (Google 2016)](https://github.com/wzhe06/Ad-papers/blob/master/Deep%20Learning%20CTR%20Prediction/%5BWide%20%26%20Deep%5D%20Wide%20%26%20Deep%20Learning%20for%20Recommender%20Systems%20%28Google%202016%29.pdf) \u003cbr /\u003e\n* [[xDeepFM] xDeepFM - Combining Explicit and Implicit Feature Interactions for Recommender Systems (USTC 2018)](https://github.com/wzhe06/Ad-papers/blob/master/Deep%20Learning%20CTR%20Prediction/%5BxDeepFM%5D%20xDeepFM%20-%20Combining%20Explicit%20and%20Implicit%20Feature%20Interactions%20for%20Recommender%20Systems%20%28USTC%202018%29.pdf) \u003cbr /\u003e\n* [[Image CTR] Image Matters - Visually modeling user behaviors using Advanced Model Server (Alibaba 2018)](https://github.com/wzhe06/Ad-papers/blob/master/Deep%20Learning%20CTR%20Prediction/%5BImage%20CTR%5D%20Image%20Matters%20-%20Visually%20modeling%20user%20behaviors%20using%20Advanced%20Model%20Server%20%28Alibaba%202018%29.pdf) \u003cbr /\u003e\n* [[AFM] Attentional Factorization Machines - Learning the Weight of Feature Interactions via Attention Networks (ZJU 2017)](https://github.com/wzhe06/Ad-papers/blob/master/Deep%20Learning%20CTR%20Prediction/%5BAFM%5D%20Attentional%20Factorization%20Machines%20-%20Learning%20the%20Weight%20of%20Feature%20Interactions%20via%20Attention%20Networks%20%28ZJU%202017%29.pdf) \u003cbr /\u003e\n* [[DIEN] Deep Interest Evolution Network for Click-Through Rate Prediction (Alibaba 2019)](https://github.com/wzhe06/Ad-papers/blob/master/Deep%20Learning%20CTR%20Prediction/%5BDIEN%5D%20Deep%20Interest%20Evolution%20Network%20for%20Click-Through%20Rate%20Prediction%20%28Alibaba%202019%29.pdf) \u003cbr /\u003e\n* [[DSSM] Learning Deep Structured Semantic Models for Web Search using Clickthrough Data (UIUC 2013)](https://github.com/wzhe06/Ad-papers/blob/master/Deep%20Learning%20CTR%20Prediction/%5BDSSM%5D%20Learning%20Deep%20Structured%20Semantic%20Models%20for%20Web%20Search%20using%20Clickthrough%20Data%20%28UIUC%202013%29.pdf) \u003cbr /\u003e\n* [[FNN] Deep Learning over Multi-field Categorical Data (UCL 2016)](https://github.com/wzhe06/Ad-papers/blob/master/Deep%20Learning%20CTR%20Prediction/%5BFNN%5D%20Deep%20Learning%20over%20Multi-field%20Categorical%20Data%20%28UCL%202016%29.pdf) \u003cbr /\u003e\n* [[DeepFM] A Factorization-Machine based Neural Network for CTR Prediction (HIT-Huawei 2017)](https://github.com/wzhe06/Ad-papers/blob/master/Deep%20Learning%20CTR%20Prediction/%5BDeepFM%5D%20A%20Factorization-Machine%20based%20Neural%20Network%20for%20CTR%20Prediction%20%28HIT-Huawei%202017%29.pdf) \u003cbr /\u003e\n* [[NFM] Neural Factorization Machines for Sparse Predictive Analytics (NUS 2017)](https://github.com/wzhe06/Ad-papers/blob/master/Deep%20Learning%20CTR%20Prediction/%5BNFM%5D%20Neural%20Factorization%20Machines%20for%20Sparse%20Predictive%20Analytics%20%28NUS%202017%29.pdf) \u003cbr /\u003e\n\n## 其他相关资源\n* [Papers on Computational Advertising](https://github.com/wzhe06/Ad-papers) \u003cbr /\u003e\n* [Papers on Recommender System](https://github.com/wzhe06/Ad-papers) \u003cbr /\u003e\n* [CTR Model Based on Spark](https://github.com/wzhe06/SparkCTR) \u003cbr /\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fwzhe06%2Fsparrowrecsys","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fwzhe06%2Fsparrowrecsys","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fwzhe06%2Fsparrowrecsys/lists"}